We describe for dependency parsing an annotation adaptation strategy, which can automatically transfer the knowledge from a source corpus with a different annotation standard to the desired target parser, with the sup...
详细信息
We describe a method for filtering object category from a large number of noisy images. This problem is particularly difficult due to the greater variation within object categories and lack of labeled object images. O...
详细信息
ISBN:
(纸本)9781424456536;9781424456543
We describe a method for filtering object category from a large number of noisy images. This problem is particularly difficult due to the greater variation within object categories and lack of labeled object images. Our method deals with it by combining a co-training algorithm CoBoost [7] with two features - 1st and 2nd order features, which define bag of words representation and spatial relationship between local features respectively. We iteratively train two boosting classifiers based on the 1st and 2nd order features, during which each classifier provides labeled data for the other classifier. It is effective because the 1st and 2nd order features make up an independent and redundant feature split. We evaluate our method on Berg dataset and demonstrate the precision comparative to the state-of-the-art.
This paper describes the ICT Statistical Machine Translation systems that used in the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2009. For this year's evaluation, we p...
详细信息
Efficient coding hypothesis provides a quantitative relationship between environmental statistics and neural processing. In this paper, we put forward a novel sparse coding model based on structural similarity (SS-SC)...
详细信息
In this paper we present a feature extraction approach by using ICA filters bank, which consists of the ICA basis images learned from the training images. On the basis of its ability to capture the inherent properties...
详细信息
Zadeh proposed that there are three basic concepts that underlie human cognition: granulation, organization and causation and a granule being a clump of points (objects) drawn together by indistinguishability, similar...
详细信息
Zadeh proposed that there are three basic concepts that underlie human cognition: granulation, organization and causation and a granule being a clump of points (objects) drawn together by indistinguishability, similarity, proximity or functionality. In this paper, we give out a novel definition of Granular computing which can be easily treated by neural network. Perception learning as granular computing tries to study the machine learning from perception information sampling to dimensional reduction and samples classification in a granular way, and can be summaries as two kind approaches:(1) covering learning, (2) svm kind learning. We proved that although there are tremendous algorithms for dimensional reduction and information transformation, their ability can't transcend wavelet kind nested layered granular computing which are very easy for neural network processing.
Synthetic aperture radar (SAR) images are inherently affected by multiplicative speckle noise, which is due to the coherent nature of scattering phenomena. This paper presents a despeckling method for SAR images based...
详细信息
Word sense disambiguation (WSD) suffers from the lack of large scale corpus which annotated with word senses. The reason is that creating this corpus with human annotation is time-consuming and expensive. Active learn...
详细信息
This paper presents a framework that actively selects informative documents pairs for semi-supervised document clustering. The semi-supervised document clustering algorithm is a Constrained DBSCAN (Cons-DBSCAN), which...
详细信息
This paper presents a framework that actively selects informative documents pairs for semi-supervised document clustering. The semi-supervised document clustering algorithm is a Constrained DBSCAN (Cons-DBSCAN), which incorporates instance-level constraints to guide the clustering process in DBSCAN. By obtaining user feedbacks, our proposed active learning algorithm can get informative instance level constraints to aid clustering process. Experimental results show that Cons-DBSCAN with the proposed active learning approach can provide an appealing clustering performance.
Current tree-to-tree models suffer from parsing errors as they usually use only 1-best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model that uses packed forests. The model ...
ISBN:
(纸本)9781932432466
Current tree-to-tree models suffer from parsing errors as they usually use only 1-best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model that uses packed forests. The model is based on a probabilistic synchronous tree substitution grammar (STSG), which can be learned from aligned forest pairs automatically. The decoder finds ways of decomposing trees in the source forest into elementary trees using the source projection of STSG while building target forest in parallel. Comparable to the state-of-the-art phrase-based system Moses, using packed forests in tree-to-tree translation results in a significant absolute improvement of 3.6 BLEU points over using 1-best trees.
暂无评论